Hi,
every one, I have learn a lot from you, thanks.
But now I have encounter a new problem.
My system is Linux as 4.0, My computer is a cluster system(I do not know
what really it is, it have 76 nodes, each node has 2 cpus and 8G memory, we
call it high performance computer ).
I have intall meep-mpi, it seems no problem. (the system has install mpich
itself, and I use --with-mpi in configure command, it is ok).
but when I use "mpirun -np 8 meep-mpi ***.ctl ", I write a short
script file, to tell mpirun run meep-mpi on 8 cpus from node 1, node 2, node 3
and node 4. since each node have 2 cpus, MPI it is parallel on each node, but
not on all nodes. it means that 4 nodes computer the same ***.ctl
independently. each node computer ***.ctl itself, and two cpu on the same node
computer ***.ctl parallelly.
***.ctl have been computed fourtimes. and ***.out gives four repeated
and crossing results just like this :(below). and after one node complete the
compute, the other is still computer once more.(and when I compile
meep-mpi,after configure, it says "it seems two cpus")
Meep progress: 350.8/550.0 = 63.8% done in 13860.5s, 7870.6s to go
Meep progress: 421.1/550.0 = 76.6% done in 13877.6s, 4248.0s to go
Meep progress: 351.1/550.0 = 63.8% done in 13822.7s, 7830.6s to go
on time step 8424 (time=421.2), 1.58006 s/step
Meep progress: 421.25/550.0 = 76.6% done in 13880.3s, 4242.3s to go
on time step 8424 (time=421.2), 1.60284 s/step
on time step 7018 (time=350.9), 1.90669 s/step
on time step 7024 (time=351.2), 1.88567 s/step
Meep progress: 421.25/550.0 = 76.6% done in 13882.4s, 4243.0s to go
Meep progress: 350.95/550.0 = 63.8% done in 13866.2s, 7864.6s to go
on time step 8427 (time=421.35), 1.58911 s/step
Meep progress: 351.25/550.0 = 63.9% done in 13828.3s, 7824.6s to go
Meep progress: 421.4/550.0 = 76.6% done in 13885.0s, 4237.3s to go
on time step 8427 (time=421.35), 1.59857 s/step
on time step 7021 (time=351.05), 1.90656 s/step
...........
flux1:, 0.221212121212122, 0.106653127000874, 0.0740690775949977
flux1:, 0.223232323232324, 0.0982028363224851, 0.04068182920827
run 0 finished at t = 550.0 (11000 timesteps)
flux1:, 0.1, 3.81020287688855e-7, -1.0383157088746e-6
flux1:, 0.102020202020202, -6.32926819439359e-7, 9.62432692296767e-8
........
flux1:, 0.295959595959597, 3.1730785071257e-5, 9.23333263220093e-6
flux1:, 0.297979797979799, 2.03746838070726e-5, 9.53539244553373e-6
flux1:, 0.300000000000001, 1.23302573745633e-5, 1.12795635270881e-6
Elapsed run time = 18256 s
Meep progress: 460.05/550.0 = 83.6% done in 18112.4s, 3541.4s to go
-----------
anybody have seen this problems?
_______________________________________________
meep-discuss mailing list
[email protected]
http://ab-initio.mit.edu/cgi-bin/mailman/listinfo/meep-discuss
